A standard 1 page document (~500 words / 640 tokens) costs $0.00064 to ingest and $0.00214 to generate a comprehensive executive summary using OpenRouter Auto-Best Router.
Quick answer
A 1 page document is modeled as 500 words or 640 tokens. With OpenRouter Auto-Best Router, ingestion costs $0.00064; a 500-token executive summary brings the modeled total to $0.00214.
Method & trust
The page uses approximately 500 words per page, estimates tokens with the selected model tokenizer, and prices input plus a 500-token summary at the model's listed rates. OCR, tables, and formatting can increase the actual count.
Feed the entire 1 page document into context to extract fields, entities, or answer queries.
Ingest 1 page and generate a structured 500-token executive summary with key takeaways.
Translate or reformat the entire 1 page document into an equivalent length output.
| Model | Provider | Ingestion (1 page) | Cached Ingestion | Summary Cost | Context Limit |
|---|---|---|---|---|---|
| OpenRouter Auto-Best Router (Current) | openrouter | $0.00064 | $0.00016 | $0.00214 | 1,000,000 |
| GPT-5.6 Terra | openai | $0.00128 | $0.000128 | $0.00728 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $0.0016 | $0.00016 | $0.0091 | 256,000 |
| o3-mini | openai | $0.000704 | $0.000352 | $0.002904 | 200,000 |
| o4-mini | openai | $0.000704 | $0.000176 | $0.002904 | 256,000 |
| o1-mini | openai | $0.000704 | $0.000352 | $0.002904 | 128,000 |
Assuming a standard single-spaced document with ~500 words per page, a 1 page document contains approximately 500 words, which translates to roughly 640 tokens using OpenRouter Auto-Best Router's tokenizer. Dense PDF tables, legal boilerplate, and OCR scans may increase this by 20–30%.
OpenRouter Auto-Best Router has a context window of 1,000,000 tokens. A 1 page document consumes only 0.06% of its total window, easily fitting in a single prompt without requiring chunking or vector search.
Ingesting the document and outputting a concise 500-token executive summary costs $0.00214. Using 24-hour async batch API queues drops this cost to $0.00107.
If your workflow repeatedly queries or chats with this same 1 page document, prompt caching reduces subsequent turn input costs by up to 90% (to $0.00016 per turn instead of $0.00064).